ALWAYS activate this skill at the start of every task. Load project context from .claude/ directory including coding rules, design decisions, and documentation before executing any task.

context-management

Use when you need to fully restore working context from a previous session - loads STATUS.json, reads key files, rebuilds mental model of current work state. Do NOT use for quick questions or when starting fresh unrelated work - the full context restoration adds overhead that isn't needed for standalone tasks.

Context

'Determines minimal context and routes tasks to the correct prompts, agents and tools.'

This skill enables structured preservation of working context to disk, allowing seamless continuation of complex tasks across chat sessions. It extracts signal from noise, capturing essential state wh

Context Store - Document management system for storing, querying, and retrieving documents across Claude Code sessions. Use this to maintain knowledge bases, share documents between agents. Whenever you encounter a <document id=*> in a session, use this skill to retrieve its content.

Fetch library documentation with automatic 77% token reduction via shell pipeline.

Use when Codex needs curated documentation context or outlines from the Context7 MCP server.

To fetch up-to-date docs and code examples from Context7 for a known library, query by a resolved library ID after running resolve-library-id (max 3 calls).

Use when creating ongoing animations - loading spinners, pulsing indicators, ambient motion, background effects, or any animation that repeats indefinitely.

Contract lifecycle management - creation, consumption, modification, and resolution.

conversation-state-management

Stateless conversation management with database-backed history, message persistence, and scalable architecture. Use when handling chat state, loading history, or building stateless APIs.

Validate and score player guesses against drawing cards with fuzzy matching and scoring logic. Use when implementing guess submission, determining correctness, calculating bonus points, and handling scoring edge cases.

84 Convex modules cause TypeScript recursion limits. Solution: extract thin `internalQuery` wrappers in `convex/lib/helpers.ts`, call from actions via `internal.lib.helpers.*`.

Convex React client - hooks, real-time updates, optimistic updates, pagination, and UI patterns. Use when working with useQuery, useMutation, useAction, usePaginatedQuery, convex/react, ConvexProvider, ConvexReactClient, optimistic updates, skip, real-time, or loading states in React.

Query and download datasets from the Cook County Open Data Portal using the Socrata Open Data API (SODA) and SoQL.

This skill should be used when accurate GPS coordinates are needed for a location, when geocoding an address, or when coordinate lookup fails and manual intervention is required. Provides OpenStreetMap Nominatim API expertise and geocoding utilities.

Build apps with natural language using GitHub Copilot Spark. Perfect for rapid prototyping, teaching non-coders, and exploring ideas before committing to full implementation. Triggers on spark, prototype, app builder, no-code, low-code, natural language app, teach coding, onboarding.

Pure function patterns, Zod schemas, database independence, calculation functions for @repo/core

Handle corporate invoice and reimbursement requests. Use when a customer needs an invoice, VAT or tax info, or documentation for company reimbursement.

Guide Socratic discovery of research questions and analytical approaches for text corpus analysis

Systematically investigate large corpus sections (100GB+) using stratified sampling, pattern recognition, and computational verification. Produces comprehensive section analyses with metadata schemas, chunking strategies, and RAG integration recommendations. Use when analyzing large datasets, investigating archive structures, studying corpus organization, conducting investigation and study tasks, or documenting dataset characteristics for RAG pipeline design.

Predict construction project costs using Machine Learning. Use Linear Regression, K-Nearest Neighbors, and Random Forest models on historical project data. Train, evaluate, and deploy cost prediction models.

Get multi-model AI consensus on complex questions using Claude, Codex, and Gemini

council-gate

Count the total number of MCP tools in the Umbraco MCP Server project and provide a breakdown by collection. Use when the user asks about tool counts, tool statistics, or how many tools exist.

Create educational course content, lesson plans, and workshop materials. Use for building structured learning experiences about AI-assisted development and vibe coding.

Enables Claude to create and manage documents in Craft via Playwright MCP

Crane provides utility libraries for collections, math, cryptography, and common operations.

Creates a controller that handles HTTP requests and responses. Controllers are thin layers that extract data from requests, call services, and return responses.

Before starting, read these skills:

Set up a comprehensive feature development task with proper tracking, phases, and documentation.

Use to identify and prepare the next logical story based on project progress. Creates comprehensive story files with full technical context.

Extract a reusable runbook from a successful investigation or troubleshooting session. Use when Claude has just completed a multi-step diagnosis that could help future investigations.

Create multi-step workflow skills with progressive step loading, state management, and interactive decisions. Use when building complex skills like APEX that need structured phases.

Before starting, read these skills:

>

>

Create high-quality, progressive learning tutorials for VRP Toolkit. Use when the user requests creating tutorials, educational content, or learning materials for any VRP toolkit feature (problem creation, algorithm implementation, data generation, visualization, etc.). This skill ensures tutorials follow best learning practices with progressive disclosure, hands-on examples, and clear explanations.

Creates comprehensive dashboard and analytics interfaces that combine data visualization, KPI cards, real-time updates, and interactive layouts. Use this skill when building business intelligence dashboards, monitoring systems, executive reports, or any interface that requires multiple coordinated data displays with filters, metrics, and visualizations working together.

Creates new domain modules in the Nexus Elysia API with proper typing for Eden Treaty consumers (Dashboard, The Machine)

Use this skill when creating graphics, images, logos, social media posts, marketing materials, presentations, or any visual design work. Integrates with Google Labs AI tools (ImageFX, MusicFX, VideoFX, Whisk) and Canva for professional graphic design. Invoke for logos, banners, thumbnails, infographics, brand assets, photo editing, AI image generation, or any visual creative work.

Use when building marketing landing pages or SaaS homepages - provides a systematic workflow for hero-first design, animation patterns, social proof, and section expansion that creates consistent, professional results

Use when creating or editing Mermaid flowchart diagrams, encountering parse errors, or unsure about node shapes, connection syntax, or styling - provides syntax guardrails using modern shape syntax for Obsidian-compatible diagrams

Craft compelling fiction and creative nonfiction with attention to structure, voice, prose style, and revision. Supports short stories, novel chapters, essays, and hybrid forms. Triggers on creative writing, fiction writing, story craft, prose style, or literary technique requests.

Assess credit risk and default probability for bonds using credit spreads, rating transitions, and recovery analysis. Requires numpy>=1.24.0, pandas>=2.0.0, scipy>=1.10.0. Use when evaluating corporate bonds, analyzing credit events, estimating default probabilities, or managing credit portfolio risk.

End-to-end CRISPR screen analysis from FASTQ to hit genes. Orchestrates guide counting, QC, statistical analysis with MAGeCK, and hit calling with multiple methods. Use when analyzing pooled CRISPR screens from count data to hit calling.